Physically Inspired Dense Fusion Networks for Relighting

Image relighting has emerged as a problem of signif?icant research interest inspired by augmented reality ap?plications. Physics-based traditional methods, as well asblack box deep learning models, have been developed. The existing deep networks have exploited training to achieve a new state of the art; however, they may perform poorly when training is limited or does not represent problem phe?nomenology, such as the addition or removal of dense shad?ows. We propose a model which enriches neural networks with physical insight. More precisely, our method gener?ates the relighted image with new illumination settings via two different strategies and subsequently fuses them using a weight map (w). In the first strategy, our model predicts the material reflectance parameters (albedo) and illumina?tion/geometry parameters of the scene (shading) for the re?lit image (we refer to this strategy as intrinsic image de?composition (IID)). The second strategy is solely based on the black box approach, where the model optimizes its weights based on the ground-truth images and the loss terms in the training stage and generates the relit output directly (we refer to this strategy as direct). While our pro?posed method applies to both one-to-one and any-to-any relighting problems, for each case we introduce problem?specific components that enrich the model performance: 1) For one-to-one relighting we incorporate normal vectors of the surfaces in the scene to adjust gloss and shadows ac?cordingly in the image. 2) For any-to-any relighting, we propose an additional multiscale block to the architecture to enhance feature extraction. Experimental results on the VIDIT 2020 and the VIDIT 2021 dataset (used in the NTIRE 2021 relighting challenge) reveals that our proposal can outperform many state-of-the-art methods in terms of well?known fidelity metrics and perceptual loss

A New Photographic Reproduction Method Based on Feature Fusion and Virtual Combined Histogram Equalization

A desirable photographic reproduction method should have the ability to compress high-dynamic-range images to low-dynamic-range displays that faithfully preserve all visual information. However, during the compression process, most reproduction methods face challenges in striking a balance between maintaining global contrast and retaining majority of local details in a real-world scene. To address this problem, this study proposes a new photographic reproduction method that can smoothly take global and local features into account. First, a highlight/shadow region detection scheme is used to obtain prior information to generate a weight map. Second, a mutually hybrid histogram analysis is performed to extract global/local features in parallel. Third, we propose a feature fusion scheme to construct the virtual combined histogram, which is achieved by adaptively fusing global/local features through the use of Gaussian mixtures according to the weight map. Finally, the virtual combined histogram is used to formulate the pixel-wise mapping function. As both global and local features are simultaneously considered, the output image has a natural and visually pleasing appearance. The experimental results demonstrated the effectiveness of the proposed method and the superiority over other seven state-of-the-art methods.

Families of Bianchi modular symbols: critical base-change p-adic L-functions and p-adic Artin formalism

Let K be an imaginary quadratic field. In this article, we study the eigenvariety for $$\mathrm {GL}_2/K$$ GL 2 / K , proving an étaleness result for the weight map at non-critical classical points and a smoothness result at base-change classical points. We give three main applications of this; let f be a p-stabilised newform of weight $$k \ge 2$$ k ≥ 2 without CM by K. Suppose f has finite slope at p and its base-change $$f_{/K}$$ f / K to K is p-regular. Then: (1) We construct a two-variable p-adic L-function attached to $$f_{/K}$$ f / K under assumptions on f that conjecturally always hold, in particular with no non-critical assumption on f/K. (2) We construct three-variable p-adic L-functions over the eigenvariety interpolating the p-adic L-functions of classical base-change Bianchi cusp forms. (3) We prove that these base-change p-adic L-functions satisfy a p-adic Artin formalism result, that is, they factorise in the same way as the classical L-function under Artin formalism.

Fusion of Infrared and Visible Images for Surveillance Applications using Ann

Edge preserving filters were used to Multi-Scale Decomposition (MSD) for fusion of visible and infrared images. Traditional edge preserving MSDs may be unable to achieve satisfactory structural separation from details, resulting in fusion performance degradation. The objective of this work is to propose a MSD Iteration with ANN fusion technique for infrared and visual image which improves the fusion execution. Initially the original image is decomposed by “Gaussian smoothness and joint bilateral filter”. Edge retention and scaling perception attributes are introduced to satisfactorily separate image details from source images. Decomposition includes preserving the attributes of edge and zoom perception, so that the detail information is completely separated from the image details and the improvement of fusion performance is maintained. The rule aims to merge these decomposed layers. A saliency map is constructed by Laplacian and Gaussian low-pass filters to find the initial weight map and further a guided filter is used to determine the final weight map. The enhanced fused image later obtained by using ANN, which eventually increases the act of fusion execution. This work proposes ANN based fusion algorithm for fusing visible and infrared images and obtains better performance by reducing the complexity.

Deep semi-supervised learning with weight map for review helpfulness prediction

Helpful online product reviews, which includemassive information, have large impacts on customers? purchasing decisions. In most of e-commerce plat forms, the helpfulness of reviews are decided by the votes from other customers. Making full use of these reviews with votes has enormous commercial value, especially in product recommendation. It drives researchers to study the technologies about how to evaluate the review helpfulness automatically. Although Deep Neural Network(DNN), learning from the historical reviews and labels, computed by the votes, has demonstrated effective results, it still has suffered insufficient labeled reviews problem. When the helpfulness of a large number of reviews is unknown for lack of votes, or some useful latest reviews with less votes are submerged by the past reviews, the accuracy of current DNN model decreases quickly. Therefore, we propose an end-to-end deep semi-supervised learning model with weight map, which makes full use of the unlabeled reviews. The training process in this model is divided into three stages:obtaining base classifier by less labeled reviews, iteratively applying weight map strategy on large unlabeled reviews to obtain pseudo-labeled reviews, training on above combined reviews to obtain the re-training classifier. Based on this novel model, we develop an algorithm and conduct a series of experiments, on Amazon Review Dataset, from the aspects of the baseline neural network selection and the strategies comparisons, including two labeling and three weighting strategies. The experimental results demonstrate the effectiveness of our method on utilizing the unlabeled data. And our findings show that the model adopted batch labeling strategy and non-linear weight mapping method has achieved the best performance.

Fourier Domain Anomaly Detection and Spectral Fusion for Stripe Noise Removal of TIR Imagery

Stripe noise is a common and unwelcome noise pattern in various thermal infrared (TIR) image data including conventional TIR images and remote sensing TIR spectral images. Most existing stripe noise removal (destriping) methods are often difficult to keep a good and robust efficacy in dealing with the real-life complex noise cases. In this paper, based on the intrinsic spectral properties of TIR images and stripe noise, we propose a novel two-stage transform domain destriping method called Fourier domain anomaly detection and spectral fusion (ADSF). Considering the principal frequencies polluted by stripe noise as outliers in the statistical spectrum of TIR images, our naive idea is first to detect the potential anomalies and then correct them effectively in the Fourier domain to reconstruct a desired destriping result. More specifically, anomaly detection for stripe frequencies is achieved through a regional comparison between the original spectrum and the expected spectrum that statistically follows a generalized Laplacian regression model, and then an anomaly weight map is generated accordingly. In the correction stage, we propose a guidance-image-based spectrum fusion strategy, which integrates the original spectrum and the spectrum of a guidance image via the anomaly weight map. The final reconstruction result not only has no stripe noise but also maintains image structures and details well. Extensive real experiments are performed on conventional TIR images and remote sensing spectral images, respectively. The qualitative and quantitative assessment results demonstrate the superior effectiveness and strong robustness of the proposed method.

Navigating Non-Playable Characters Based on User Trajectories with Accumulation Map and Path Similarity

In this paper, we propose a method to efficiently control the path of non-playable characters (NPC) in an interactive virtual environment such as a game or virtual reality (VR) by calculating a weight map and path similarity based on the user’s path. Our method automatically constructs a navigation mesh that provides a new route to the NPC by referring to the user’s trajectory. Our method finds more paths that users usually go through as time passes, and the number of users increases. Accordingly, the paths that NPCs can traverse automatically are updated adaptively to the virtual environment. In addition, NPC agents can move smartly by assigning high weights to the user’s preferred paths. We tested the usefulness of the proposed method through several example scenarios in an interactive environment such as a video game or VR, and this method can be easily applied to various types of navigation based on the interactive environment.

Underwater Image Enhancement using Color Balance and Fusion

We have introduced an elective way to deal with upgrade the pictures caught submerged and corrupted because of the medium dispersing and assimilation. Our technique is a solitary picture approach that doesn't require particular equipment or information about the submerged conditions or scene structure. It expands on the mixing of two pictures that are straightforwardly gotten from a shading redressed and white-adjusted rendition of the first debased picture. The two pictures to combination, just as their related weight maps, are characterized to advance the exchange of edges and shading complexity to the yield picture. To stay away from that the sharp weight map changes make ancient rarities in the low recurrence parts of the reproduced picture, we additionally adjust a multi scale combination technique. Our broad subjective and quantitative assessment uncovers that our upgraded pictures and recordings are described by better exposedness of the dull districts, improved worldwide difference, and edges sharpness. Our approval likewise demonstrates that our calculation is sensibly free of the camera settings, and improves the exactness of a few picture preparing applications.